SMSecure: Leveraging Machine Learning for Smishing Detection

The SMS facilitates the transmission of concise text messages between mobile phone users, serving a range of functions in both personal and business domains such as appointment confirmation, authentication, alerts, notifications, and banking updates. It plays a vital role in daily communication due to its accessibility, reliability, and compatibility. Its accessibility, reliability, and compatibility make it essential for daily communication. However, SMS unintentionally generates an environment where smishing can occur. This is because SMS is extensively available and reliable. Smishing attackers take advantage of this trust to deceive victims into divulging sensitive information or performing malicious actions. Early detection saves users from being victimized. Researchers introduced different methods for accurately detecting smishing attacks. Machine Learning models and Techniques for Language Processing are a promising approach for combating the escalating menace of SMS phishing attacks. By analyzing large datasets of SMS messages, machine learning models with natural language processing methods can differentiate between legitimate and fraudulent messages. To detect smishing attacks, this paper presents a method (SMSecure) that leverages machine learning models and language processing techniques. The results show that random forest and extreme gradient boosting attain higher accuracy levels.